FP Ê Ó python Ê μ Ï Ö

FP Ê Ó python Ê μ Ï Ö

FP-growth fair Fair enough · r²» äüè ¥ · ~~ömá~~~~~~£?fp-growth ~~~~~~» ~~~~~~~~****************************** ¿â ½ ø Ð ááám'é éräzäzant=» ° Ç çé ¿öö Â Æ ä Ã ¨? apriori **************************************

WHY» Why? FP then *****************************************************************

Ú ú± ð µäê û ² Ç çø ± £ £;öö» Ç çöó óáááë à like Ú úμ ã μááá 'antóbarant£.

FP limit £° <limit · limit "http://www.bkjia.com/kf/ware/vc/" target = "_ blank" class = "keylink"> vcD4KPHA + PC9wPgo8cHJlIGNsYXNzPQ = "brush: java; "> class treeNode: def _ init _ (self, nameValue, numOccur, parentNode): self. name = nameValue self. count = numOccur self. nodeLink = None self. parent = parentNode self. children = {} def inc (self, numOccur): self. count + = numOccur def disp (self, ind = 1): print ''' * ind, self. name, '', self. count for child in self. children. values (): child. disp (ind + 1)

Disp () ° ¯ Ê Ö ö÷ Ç Ä ä± ¾ Ï Ê ¾ ³ ö Ö µ? £» mööê µà £ *****************************************************************

~Â ö ö~~~~~~~ä² ~~í ~çáá?fp ~~£%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%^' úâ £°

def createTree(dataSet, minSup=1): #create FP-tree from dataset but don't mine    headerTable = {}    #go over dataSet twice    for trans in dataSet:#first pass counts frequency of occurance        for item in trans:            headerTable[item] = headerTable.get(item, 0) + dataSet[trans]    for k in headerTable.keys():  #remove items not meeting minSup        if headerTable[k] < minSup:             del(headerTable[k])    freqItemSet = set(headerTable.keys())    #print 'freqItemSet: ',freqItemSet    if len(freqItemSet) == 0: return None, None  #if no items meet min support -->get out    for k in headerTable:        headerTable[k] = [headerTable[k], None] #reformat headerTable to use Node link     #print 'headerTable: ',headerTable    retTree = treeNode('Null Set', 1, None) #create tree    for tranSet, count in dataSet.items():  #go through dataset 2nd time        localD = {}        for item in tranSet:  #put transaction items in order            if item in freqItemSet:                localD[item] = headerTable[item][0]        if len(localD) > 0:            orderedItems = [v[0] for v in sorted(localD.items(), key=lambda p: p[1], reverse=True)]            updateTree(orderedItems, retTree, headerTable, count)#populate tree with ordered freq itemset    return retTree, headerTable #return tree and header tabledef updateTree(items, inTree, headerTable, count):    if items[0] in inTree.children:#check if orderedItems[0] in retTree.children        inTree.children[items[0]].inc(count) #incrament count    else:   #add items[0] to inTree.children        inTree.children[items[0]] = treeNode(items[0], count, inTree)        if headerTable[items[0]][1] == None: #update header table             headerTable[items[0]][1] = inTree.children[items[0]]        else:            updateHeader(headerTable[items[0]][1], inTree.children[items[0]])    if len(items) > 1:#call updateTree() with remaining ordered items        updateTree(items[1::], inTree.children[items[0]], headerTable, count)        def updateHeader(nodeToTest, targetNode):   #this version does not use recursion    while (nodeToTest.nodeLink != None):    #Do not use recursion to traverse a linked list!        nodeToTest = nodeToTest.nodeLink    nodeToTest.nodeLink = targetNode

2. Please refer to the comment below × ******************************************************** headerTable guímoçí ö¸ ë ± ±í£%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% · ± Ï î ¼ öð Ó µ μ Ö ×ö× ± £ ££ â À Ó Ò» Ð µ μ ï ö¸ ~~ú~« Î £;%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%â ú× ã × µ µíö§ Ö öant=£%ö± ½ Ó É µ μ ²» ó~~~~~~~£updatetree () ° too many bytes before ± ¸ ü Ð Â £ £%%updateheader () Ç ¬» then headerTable Í ö¸ %%%%± í %£

Ó Ò» ¿Ã FP Ê öð íú¾ ò µ?

class treeNode :    def __init__(self,nameValue,numOccur,parentNode):        self.name = nameValue        self.count = numOccur        self.nodeLink = None        self.parent = parentNode        self.children = {}    def inc (self,numOccur):        self.count += numOccur            def disp(self,ind = 1):        print ' '*ind,self.name,'  ',self.count        for child in self.children.values():            child.disp(ind+1)def createTree(dataSet,minSup=1):    headerTable = {}    for trans in dataSet:        for item in trans:            headerTable[item] = headerTable.get(item,0)+ dataSet[trans]    for k in headerTable.keys():        if headerTable[k] < minSup:            del(headerTable[k])      freqItemSet = set(headerTable.keys())    if len(freqItemSet) == 0 : return None,None    for k in headerTable:        headerTable[k] = [headerTable[k],None]    retTree = treeNode('Null Set',1,None)    for tranSet ,count in dataSet.items():        localD = {}        for item in tranSet:            if item in freqItemSet:                localD[item] = headerTable[item][0]        if len(localD) > 0:            orderedItems = [v[0] for v in sorted(localD.items(),key = lambda p:p[1],reverse = True)]            updateTree(orderedItems,retTree,headerTable,count)    return retTree,headerTabledef updateTree(items,inTree,headerTable,count):    if items[0] in inTree.children:        inTree.children[items[0]].inc(count)    else:        inTree.children[items[0]] = treeNode(items[0],count,inTree)        if headerTable[items[0]][1] ==None:            headerTable[items[0]][1] = inTree.children[items[0]]        else:            updateHeader(headerTable[items[0]][1], inTree.children[items[0]])    if len(items) > 1:        updateTree(items[1::], inTree.children[items[0]], headerTable, count)        def updateHeader(nodeToTest,targetNode):    while (nodeToTest.nodeLink !=  None):        nodeToTest = nodeToTest.nodeLink    nodeToTest.nodeLink = targetNode    def loadSimpDat():    simpDat = [['r', 'z', 'h', 'j', 'p'],               ['z', 'y', 'x', 'w', 'v', 'u', 't', 's'],               ['z'],               ['r', 'x', 'n', 'o', 's'],               ['y', 'r', 'x', 'z', 'q', 't', 'p'],               ['y', 'z', 'x', 'e', 'q', 's', 't', 'm']]    return simpDatdef createInitSet(dataSet):    retDict = {}    for trans in dataSet:        retDict[frozenset(trans)] = 1    return retDictdef ascendTree(leafNode,prefixPath):    if leafNode.parent !=None:        prefixPath.append(leafNode.name)        ascendTree(leafNode.parent, prefixPath)def findPrefixPath(basePat,treeNode):    condPats={}    while treeNode != None:        prefixPath = []        ascendTree(treeNode, prefixPath)        if len(prefixPath) > 1:            condPats[frozenset(prefixPath[1:])] = treeNode.count        treeNode = treeNode.nodeLink    return condPatsdef mineTree(inTree,headerTable,minSup,preFix,freqItemList):    bigL = [v[0] for v in sorted(headerTable.items(),key=lambda p:p[1])]    for basePat in bigL:        newFreqSet = preFix.copy()        newFreqSet.add(basePat)        freqItemList.append(newFreqSet)        condPattBases = findPrefixPath(basePat, headerTable[basePat][1])        myCondTree,myHead = createTree(condPattBases, minSup)         if myHead!= None:            print 'conditional tree for: ',newFreqSet            myCondTree.disp(1)             mineTree(myCondTree, myHead, minSup, newFreqSet, freqItemList)   if __name__ == "__main__":    simpDat = loadSimpDat()    print simpDat    initSet = createInitSet(simpDat)    print initSet    myFPtree , myHeaderTab = createTree(initSet, 3)    myFPtree.disp()    print findPrefixPath('t', myHeaderTab['t'][1])    freqItems = []    mineTree(myFPtree, myHeaderTab, 3, set([]), freqItems)    print freqItems    

Ê ämömámím=£°

[['r', 'z', 'h', 'j', 'p'], ['z', 'y', 'x', 'w', 'v', 'u', 't', 's'], ['z'], ['r', 'x', 'n', 'o', 's'], ['y', 'r', 'x', 'z', 'q', 't', 'p'], ['y', 'z', 'x', 'e', 'q', 's', 't', 'm']]{frozenset(['e', 'm', 'q', 's', 't', 'y', 'x', 'z']): 1, frozenset(['x', 's', 'r', 'o', 'n']): 1, frozenset(['s', 'u', 't', 'w', 'v', 'y', 'x', 'z']): 1, frozenset(['q', 'p', 'r', 't', 'y', 'x', 'z']): 1, frozenset(['h', 'r', 'z', 'p', 'j']): 1, frozenset(['z']): 1}  Null Set    1   x    1    s    1     r    1   z    5    x    3     y    3      s    2       t    2      r    1       t    1    r    1{frozenset(['y', 'x', 's', 'z']): 2, frozenset(['y', 'x', 'r', 'z']): 1}conditional tree for:  set(['y'])  Null Set    1   x    3    z    3conditional tree for:  set(['y', 'z'])  Null Set    1   x    3conditional tree for:  set(['s'])  Null Set    1   x    3conditional tree for:  set(['t'])  Null Set    1   y    3    x    3     z    3conditional tree for:  set(['x', 't'])  Null Set    1   y    3conditional tree for:  set(['z', 't'])  Null Set    1   y    3    x    3conditional tree for:  set(['x', 'z', 't'])  Null Set    1   y    3conditional tree for:  set(['x'])  Null Set    1   z    3[set(['y']), set(['y', 'x']), set(['y', 'z']), set(['y', 'x', 'z']), set(['s']), set(['x', 's']), set(['t']), set(['y', 't']), set(['x', 't']), set(['y', 'x', 't']), set(['z', 't']), set(['y', 'z', 't']), set(['x', 'z', 't']), set(['y', 'x', 'z', 't']), set(['r']), set(['x']), set(['x', 'z']), set(['z'])]